© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 111232
    Prev
    Next
    INDEX
    Explanations

    code structure and function definitions in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    private, exclusive, custom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.94
     '\\;'
    -0.82
     المعيارى
    -0.81
    endphp
    -0.73
     MainAxisSize
    -0.72
    FieldBuilder
    -0.67
    localctx
    -0.65
    SequentialGroup
    -0.65
     surla
    -0.64
     pinulongan
    -0.63
    POSITIVE LOGITS
     personalizadas
    0.40
     exclusivas
    0.37
     exclusivo
    0.37
    private
    0.36
     exclusivos
    0.35
     unique
    0.33
     private
    0.32
     year
    0.31
    tag
    0.31
     custom
    0.30
    Activations Density 0.023%

    No Known Activations